{"id":"W4402916113","doi":"10.1109/cvprw63382.2024.00211","title":"VMCML: Video and Music Matching via Cross-Modality Lifting","year":2024,"lang":"en","type":"article","venue":"","topic":"Music and Audio Processing","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Modality (human–computer interaction); Computer science; Matching (statistics); Computer vision; Artificial intelligence; Speech recognition; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001135265,0.001061166,0.001278426,0.002258501,0.0005420922,0.001233057,0.002157355,0.001412299,0.00628964],"category_scores_gemma":[0.003119025,0.000338594,0.0009925432,0.001973585,0.0005482678,0.002694477,0.003677043,0.001502683,0.004270454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004650674,"about_ca_system_score_gemma":0.0007364177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003279705,"about_ca_topic_score_gemma":0.003889504,"domain_scores_codex":[0.9986796,0.0001778439,0.00006441849,0.0004012805,0.0005134913,0.0001634321],"domain_scores_gemma":[0.9993331,0.00009419862,0.00008188288,0.0002430683,0.0001788585,0.00006897938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006713148,0.0004119512,0.002234336,0.0002440806,0.0001422865,0.0002398935,0.0001102818,0.01261139,0.07401364,0.00502875,0.01465301,0.8896391],"study_design_scores_gemma":[0.0001095823,0.0005320287,0.003705939,0.00006180527,0.00008621661,0.0008969014,0.0002011302,0.900566,0.06541702,0.01130541,0.01702649,0.00009150879],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02388546,0.0006322693,0.9651983,0.0001562213,0.0001601756,0.0002096482,0.0005873272,0.006011225,0.003159308],"genre_scores_gemma":[0.2736599,0.0005696248,0.7103162,0.0007242619,0.0002331125,0.000321948,0.003878227,0.0005060944,0.009790581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00628964,"threshold_uncertainty_score":0.02104092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01991925318231961,"score_gpt":0.2848456987159592,"score_spread":0.2649264455336395,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}